[GH-ISSUE #11733] llama runner process has terminated: error:failed to allocate buffer - #7771

Closed
opened 2026-04-12 19:55:50 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @vorticalbox on GitHub (Aug 6, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/11733

What is the issue?

when running gpt-oss:20b ollama run gpt-oss:20b llama running gets terminated.

Relevant log output

Error: 500 Internal Server Error: llama runner process has terminated: error:failed to allocate buffer, size = 33074.89 MiB
ggml_gallocr_reserve_n: failed to allocate Metal buffer of size 34681522080

OS

macOS

GPU

Apple

CPU

Apple

Ollama version

0.11.2

Originally created by @vorticalbox on GitHub (Aug 6, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/11733 ### What is the issue? when running gpt-oss:20b `ollama run gpt-oss:20b` llama running gets terminated. ### Relevant log output ```shell Error: 500 Internal Server Error: llama runner process has terminated: error:failed to allocate buffer, size = 33074.89 MiB ggml_gallocr_reserve_n: failed to allocate Metal buffer of size 34681522080 ``` ### OS macOS ### GPU Apple ### CPU Apple ### Ollama version 0.11.2
GiteaMirror added the bug label 2026-04-12 19:55:50 -05:00
Author
Owner

@vorticalbox commented on GitHub (Aug 6, 2025):

this was my fault I had the context window up to high

<!-- gh-comment-id:3159772445 --> @vorticalbox commented on GitHub (Aug 6, 2025): this was my fault I had the context window up to high
Author
Owner

@zhangjustin commented on GitHub (Aug 7, 2025):

You saved my life

<!-- gh-comment-id:3162874299 --> @zhangjustin commented on GitHub (Aug 7, 2025): You saved my life
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#7771